{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TWSB2MEART23IZS7LGTUZZ4EEX","short_pith_number":"pith:TWSB2MEA","schema_version":"1.0","canonical_sha256":"9da41d30808cf5b4665f59a74ce78425d6f8cb361929a9d9eda01ce92e1f5a4b","source":{"kind":"arxiv","id":"2003.00306","version":2},"attestation_state":"computed","paper":{"title":"Dimension-free convergence rates for gradient Langevin dynamics in RKHS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.PR","authors_text":"Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki","submitted_at":"2020-02-29T17:14:13Z","abstract_excerpt":"Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable attention lately, as a way to provide convergence guarantees in a non-convex setting. However, the known rates grow exponentially with the dimension of the space. In this work, we provide a convergence analysis of GLD and SGLD when the optimization space is an infinite dimensional Hilbert space. More precisely, we derive non-asymptotic, dimension-free convergence rates for GLD/SGLD when performing regularized non-convex optimization in a reproducing kernel Hilbert space. Amongst others, the convergence analy"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2003.00306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2020-02-29T17:14:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"38fd50a0e1366274b678b10bba98296cfe70ecc8acfee17a1ebf5eb5ce3656f2","abstract_canon_sha256":"f6d3dce34b9ad7dfa9fb595ef5df7af824e9ecbce7c64e6a89e1603331339176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:45.375773Z","signature_b64":"NV1Wg6Qb4GfudjHTGaI0MSgy67+YVdvjlOnoTSgEddVSiDW3dh9CpW4ulmOHQ95a7go3NcDwQaLir5RiQAvDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9da41d30808cf5b4665f59a74ce78425d6f8cb361929a9d9eda01ce92e1f5a4b","last_reissued_at":"2026-07-05T00:50:45.375358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:45.375358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension-free convergence rates for gradient Langevin dynamics in RKHS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.PR","authors_text":"Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki","submitted_at":"2020-02-29T17:14:13Z","abstract_excerpt":"Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable attention lately, as a way to provide convergence guarantees in a non-convex setting. However, the known rates grow exponentially with the dimension of the space. In this work, we provide a convergence analysis of GLD and SGLD when the optimization space is an infinite dimensional Hilbert space. More precisely, we derive non-asymptotic, dimension-free convergence rates for GLD/SGLD when performing regularized non-convex optimization in a reproducing kernel Hilbert space. Amongst others, the convergence analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00306","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.00306/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2003.00306","created_at":"2026-07-05T00:50:45.375416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.00306v2","created_at":"2026-07-05T00:50:45.375416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00306","created_at":"2026-07-05T00:50:45.375416+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWSB2MEART23","created_at":"2026-07-05T00:50:45.375416+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWSB2MEART23IZS7","created_at":"2026-07-05T00:50:45.375416+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWSB2MEA","created_at":"2026-07-05T00:50:45.375416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX","json":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX.json","graph_json":"https://pith.science/api/pith-number/TWSB2MEART23IZS7LGTUZZ4EEX/graph.json","events_json":"https://pith.science/api/pith-number/TWSB2MEART23IZS7LGTUZZ4EEX/events.json","paper":"https://pith.science/paper/TWSB2MEA"},"agent_actions":{"view_html":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX","download_json":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX.json","view_paper":"https://pith.science/paper/TWSB2MEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.00306&json=true","fetch_graph":"https://pith.science/api/pith-number/TWSB2MEART23IZS7LGTUZZ4EEX/graph.json","fetch_events":"https://pith.science/api/pith-number/TWSB2MEART23IZS7LGTUZZ4EEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX/action/storage_attestation","attest_author":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX/action/author_attestation","sign_citation":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX/action/citation_signature","submit_replication":"https://pith.science/pith/TWSB2MEART23IZS7LGTUZZ4EEX/action/replication_record"}},"created_at":"2026-07-05T00:50:45.375416+00:00","updated_at":"2026-07-05T00:50:45.375416+00:00"}